HOME ABOUT CONTACT AVAILABLE ISSUES SUBSCRIBE MEDIA & ADS
LATEST UPDATES » Vol 25, No. 01, January 2021 – Home-Based Diagnostic Testing: Revolutionizing IBD Treatment       » Study Reveals Understanding of China’s Carbon Emission Balance       » Developing Nanomaterials for Better Performance       » Helping Farmers Monitor Plant Health and Improve Crop Yield       » Protecting the Brain through Gut-Trained Immune Cells       » Using Machine Learning to Predict Anti-Cancer Drug Efficacy      
Vol 25, No. 01, January 2021   |   Issue PDF view/purchase
BIOBOARD
Using Machine Learning to Predict Anti-Cancer Drug Efficacy
Researchers from the Pohang University of Science and Technology (POSTECH) develop machine learning algorithms for the programme to learn from datasets close to a real patients’ response to predict the efficacy of anti-cancer drugs.

With the advent of pharmacogenomics, machine learning research has been making progress to predict the patients' drug response that varies by individual from the algorithms derived from previously collected data on drug responses. Entering high-quality learning data that can reflect a person's drug response as much as possible is the starting point for improving the accuracy of the prediction. Previously, animal models were used for preclinical studies, which were relatively easier to obtain compared to human clinical data.

A research team led by Professor Sanguk Kim in the Department of Life Sciences at POSTECH were able to successfully increase the accuracy of anti-cancer drug response predictions by using data closest to a real patients’ response. The team developed this machine learning technique through algorithms that learn the transcriptome information from artificial organoids derived from actual patients instead of animal models. These research findings were published in the international journal Nature Communications.

Patients with the same cancer could have different reactions to anti-cancer drugs, making the development of customized treatments is to be considered paramount. However, the current predictions were based on genetic information of cancer cells, limiting their accuracy. Due to unnecessary biomarker information, machine learning had an issue of learning based on false signals.

To increase the predictive accuracy, the research team introduced machine learning algorithms that use protein interaction network that can interact with target proteins as well as the transcriptome of individual proteins that are directly related with drug targets. It induces learning of the transcriptome production of a protein that is functionally close to the target protein. Through this, only selected biomarkers can be learned instead of false biomarkers that the conventional machine learning had to learn, which increases the accuracy.

In addition, data from patient-derived organoids - not animal models - were used to narrow the discrepancy of responses in actual patients. With this method, colorectal cancer patients treated with 5-fluorouracil and bladder cancer patients treated with cisplatin were predicted to be comparable to actual clinical results.

NEWS CRUNCH  
news Highlights from the E&L China 2020 Conference
news Asia’s ageing population drives development of rehabilitation technologies targeting elderly disabilities
news Virtual Expo Connect to empower access for international pharma to the world’s largest pharma ingredients market
news WEIPU, AstraZeneca, Huadong Medicine, Saint-Gobain, Baxter, Wuxi AppTec, Henlius, Medtronic and more confirmed to speak at E&L China this December
SPOTLIGHT  

MAGAZINE TAGS
About Us
Events
Available issues
Editorial Board
Letters to Editor
Contribute to APBN
Advertise with Us
CONTACT
World Scientific Publishing Co. Pte. Ltd.
5 Toh Tuck Link, Singapore 596224
Tel: 65-6466-5775
Fax: 65-6467-7667
» For Editorial Enquiries:
   biotech_edit@wspc.com or Ms Deborah Seah
» For Subscriptions, Advertisements &
   Media Partnerships Enquiries:
   biotech_ad@wspc.com
Copyright© 2021 World Scientific Publishing Co Pte Ltd  •  Privacy Policy